{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T05:01:02Z","timestamp":1785387662675,"version":"3.55.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62404256"],"award-info":[{"award-number":["62404256"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20241206180301003"],"award-info":[{"award-number":["JCYJ20241206180301003"]}]},{"name":"Jiangsu Province Major Scientific Project","award":["BG2024032"],"award-info":[{"award-number":["BG2024032"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. I"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tcsi.2026.3690706","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T20:01:43Z","timestamp":1778788903000},"page":"5583-5596","source":"Crossref","is-referenced-by-count":0,"title":["EMSTrans: An Efficient Hardware Accelerator for Transformer With Multi-Level Sparsity Awareness"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2749-420X","authenticated-orcid":false,"given":"Dingyang","family":"Zou","sequence":"first","affiliation":[{"name":"Nanjing University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baichen","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiye","family":"Ding","sequence":"additional","affiliation":[{"name":"Nanjing University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9553-3640","authenticated-orcid":false,"given":"Meiqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7227-4786","authenticated-orcid":false,"given":"Zhongfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref3","first-page":"1","article-title":"An image is worth 16$\\times$\n16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071027"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247913"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213542"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213521"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3315060"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS58744.2024.10557837"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2022.3197282"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.484"},{"key":"ref13","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023","journal-title":"arXiv:2303.12712"},{"key":"ref14","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref15","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00048"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01565"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2023.3305663"},{"key":"ref20","volume-title":"FasterTransformer","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575747"},{"key":"ref22","first-page":"1","article-title":"Lite transformer with long-short range attention","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/app15020586"},{"key":"ref24","article-title":"LLM inference unveiled: Survey and roofline model insights","author":"Yuan","year":"2024","journal-title":"arXiv:2402.16363"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2016.2612638"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42615.2023.10067360"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i21.34385"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2022.3216735"},{"key":"ref31","article-title":"QLLM: Accurate and efficient low-bitwidth quantization for large language models","author":"Liu","year":"2023","journal-title":"arXiv:2310.08041"},{"key":"ref32","article-title":"EfficientQAT: Efficient quantization-aware training for large language models","author":"Chen","year":"2024","journal-title":"arXiv:2407.11062"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00030"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00067"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3312775"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071047"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.3002564"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2024.3426653"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2023.3341348"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3310916"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2025.3547732"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00799"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3059962"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref47","first-page":"5506","article-title":"I-BERT: Integer-only BERT quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1144"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/s16-1081"}],"container-title":["IEEE Transactions on Circuits and Systems I: Regular Papers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8919\/11627725\/11520552.pdf?arnumber=11520552","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T04:52:39Z","timestamp":1785387159000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11520552\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":50,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsi.2026.3690706","relation":{},"ISSN":["1549-8328","1558-0806"],"issn-type":[{"value":"1549-8328","type":"print"},{"value":"1558-0806","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}